Search Strategy
Turn one natural-language question into parallel, source-specific enterprise searches and a single synthesized answer.
Overview
Search Strategy is an agent skill most often used in Idea (also Operate, Grow) that decomposes natural-language questions into parallel, source-specific searches and ranked synthesis.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill search-strategyWhat is this skill?
- Query-type table covering Decision, Status, and related strategies with per-source prioritization
- Decomposes one NL question into parallel semantic and filtered searches per connected connector
- Translates user intent into source-specific syntax (channels, date filters, workspace scopes)
- Ranks, deduplicates, and synthesizes multi-source hits into one coherent answer
- Handles ambiguity and fallback when connectors from CONNECTORS.md are missing or thin
- Documented query-type strategy table with Decision and Status archetypes plus parallel per-source query examples
Adoption & trust: 3.1k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Critical decisions and project status live in different tools, so one vague search string misses the channel, date, or doc type where the answer actually lives.
Who is it for?
Solo builders running knowledge-work plugins who need decision tracing and status answers across Slack-like chat, wikis, and task systems.
Skip if: Simple public-web-only research with no connected sources or users who want a single-query Google replacement without connector setup.
When should I use this skill?
A natural language question must be answered from multiple connected workplace sources with ranked, deduplicated synthesis.
What do I get? / Deliverables
You get ranked, deduplicated evidence across connected sources and a single synthesized answer aligned to query type instead of a pile of irrelevant snippets.
- Per-source query plan with syntax variants
- Ranked result set and synthesized narrative answer
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Decision and status questions start in Idea research before you commit to build scope, even though the same orchestration helps later retrospectives. Research is the canonical shelf for decomposing “what did we decide” and competitor-style knowledge pulls across chat, docs, and trackers.
Where it fits
Trace when engineering decided the API migration cutoff before you rewrite the roadmap.
Pull prior specs from wikis and threads to bound MVP scope without re-litigating settled choices.
Answer what broke last sprint by searching incidents in chat and linked tickets together.
Summarize recurring customer objections mentioned across support channels and internal notes.
How it compares
Multi-source query orchestration for connected workplace tools—not a standalone SEO keyword skill or a raw MCP install guide.
Common Questions / FAQ
Who is search-strategy for?
Builders and operators using knowledge-work-plugins who need the agent to search chat, docs, and trackers intelligently rather than one generic query.
When should I use search-strategy?
Use it during Idea research for prior decisions, Validate scoping when tracing requirements history, Operate when auditing what shipped, and Grow when summarizing customer or internal feedback threads.
Is search-strategy safe to install?
Check the Security Audits panel on this page; the skill implies searching connected accounts so confirm connector scopes and avoid exfiltrating private channels you should not query.
SKILL.md
READMESKILL.md - Search Strategy
# Search Strategy > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). The core intelligence behind enterprise search. Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results. ## The Goal Turn this: ``` "What did we decide about the API migration timeline?" ``` Into targeted searches across every connected source: ``` ~~chat: "API migration timeline decision" (semantic) + "API migration" in:#engineering after:2025-01-01 ~~knowledge base: semantic search "API migration timeline decision" ~~project tracker: text search "API migration" in relevant workspace ``` Then synthesize the results into a single coherent answer. ## Query Decomposition ### Step 1: Identify Query Type Classify the user's question to determine search strategy: | Query Type | Example | Strategy | |-----------|---------|----------| | **Decision** | "What did we decide about X?" | Prioritize conversations (~~chat, email), look for conclusion signals | | **Status** | "What's the status of Project Y?" | Prioritize recent activity, task trackers, status updates | | **Document** | "Where's the spec for Z?" | Prioritize Drive, wiki, shared docs | | **Person** | "Who's working on X?" | Search task assignments, message authors, doc collaborators | | **Factual** | "What's our policy on X?" | Prioritize wiki, official docs, then confirmatory conversations | | **Temporal** | "When did X happen?" | Search with broad date range, look for timestamps | | **Exploratory** | "What do we know about X?" | Broad search across all sources, synthesize | ### Step 2: Extract Search Components From the query, extract: - **Keywords**: Core terms that must appear in results - **Entities**: People, projects, teams, tools (use memory system if available) - **Intent signals**: Decision words, status words, temporal markers - **Constraints**: Time ranges, source hints, author filters - **Negations**: Things to exclude ### Step 3: Generate Sub-Queries Per Source For each available source, create one or more targeted queries: **Prefer semantic search** for: - Conceptual questions ("What do we think about...") - Questions where exact keywords are unknown - Exploratory queries **Prefer keyword search** for: - Known terms, project names, acronyms - Exact phrases the user quoted - Filter-heavy queries (from:, in:, after:) **Generate multiple query variants** when the topic might be referred to differently: ``` User: "Kubernetes setup" Queries: "Kubernetes", "k8s", "cluster", "container orchestration" ``` ## Source-Specific Query Translation ### ~~chat **Semantic search** (natural language questions): ``` query: "What is the status of project aurora?" ``` **Keyword search:** ``` query: "project aurora status update" query: "aurora in:#engineering after:2025-01-15" query: "from:<@UserID> aurora" ``` **Filter mapping:** | Enterprise filter | ~~chat syntax | |------------------|--------------| | `from:sarah` | `from:sarah` or `from:<@USERID>` | | `in:engineering` | `in:engineering` | | `after:2025-01-01` | `after:2025-01-01` | | `before:2025-02-01` | `before:2025-02-01` | | `type:thread` | `is:thread` | | `type:file` | `has:file` | ### ~~knowledge base (Wiki) **Semantic search** — Use for conceptual queries: ``` descriptive_query: "API migration timeline and decision rationale" ``` **Keyword search** — Use for exact terms: ``` query: "API migration" query: "\"API migration timeline\"" (exact phrase) ``` ### ~~project tracker **Task search:** ``` text: "API migration" workspace: [workspace_id] completed: false (for status